Accepted author manuscript, 787 KB, PDF document
Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
A Semi-Supervised Deep Rule-Based Approach for Remote Sensing Scene Classication. / Gu, Xiaowei; Angelov, Plamen Parvanov.
The 2019 INNS Big Data and Deep Learning (INNSBDDL 2019) conference. Springer, 2019. p. 257-266.Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - A Semi-Supervised Deep Rule-Based Approach for Remote Sensing Scene Classication
AU - Gu, Xiaowei
AU - Angelov, Plamen Parvanov
PY - 2019/4/3
Y1 - 2019/4/3
N2 - This paper proposes a new approach that is based on the recently introduced semi-supervised deep rule-based classifier for remote sensing scene classification. The proposed approach employs a pre-trained deep convoluational neural network as the feature descriptor to extract high-level discriminative semantic features from the sub-regions of the remote sensing images. This approach is able to self-organize a set of prototype-based IF...THEN rules from few labeled training images through an efficient supervised initialization process, and continuously self-updates the rule base with the unlabeled images in an unsupervised, autonomous, transparent and human-interpretable manner. Highly accurate classification on the unlabeled images is performed at the end of the learning process. Numerical examples demonstrate that the proposed approach is a strong alternative to the state-of-the-art ones.
AB - This paper proposes a new approach that is based on the recently introduced semi-supervised deep rule-based classifier for remote sensing scene classification. The proposed approach employs a pre-trained deep convoluational neural network as the feature descriptor to extract high-level discriminative semantic features from the sub-regions of the remote sensing images. This approach is able to self-organize a set of prototype-based IF...THEN rules from few labeled training images through an efficient supervised initialization process, and continuously self-updates the rule base with the unlabeled images in an unsupervised, autonomous, transparent and human-interpretable manner. Highly accurate classification on the unlabeled images is performed at the end of the learning process. Numerical examples demonstrate that the proposed approach is a strong alternative to the state-of-the-art ones.
U2 - 10.1007/978-3-030-16841-4_27
DO - 10.1007/978-3-030-16841-4_27
M3 - Conference contribution/Paper
SN - 9783030168407
SP - 257
EP - 266
BT - The 2019 INNS Big Data and Deep Learning (INNSBDDL 2019) conference
PB - Springer
T2 - INNS Conference on Big Data and Deep Learning
Y2 - 16 April 2019
ER -